Home
Subjects
Textbook solutions
Create
Study sets, textbooks, questions
Log in
Sign up
Upgrade to remove ads
Only $35.99/year
Lecture 7 - Visual Object Detection
STUDY
Flashcards
Learn
Write
Spell
Test
PLAY
Match
Gravity
Terms in this set (17)
What is the difference between Object recognition task and Object detection task?
Object recognition task:
- Is there a dog or a sofa in the image?
Object detection task:
- Where are the dog and the sofa in the image?
List some ways of evaluate object detection
1) >= 0.5 Intersection over Union (IoU)
2) Precision
#True detections/#Detections
3) Recall
#True detections/#Positive examples
What are the classical steps in a Object detection process?
1) Object Model Specification
2) Hypothesis Generation
3) Hypothesis description and scoring
4) Detection Refinement
List some Object models
1) Statistical template in bounding box
- Template visualization is used for bounding box
- Object (x, y, w, h) in image
2) Articulated parts model
- Object is configuration of parts (arm-box, leg-box etc)
- Each part can be detected
3) Hybrid model:
- Use both template and parts
List the different methods for hypothesis generation
1) Sliding window
2) Region proposal
How does sliding window works for hypothesis generation?
1) A window is sliding over the image
2) Each window is separately classified
How does region proposal work for hypothesis generation?
Find "blobby" image regions that are likely to contain objects
What are some positive and negative aspects with sliding window (hypothesis generation)?
+ Simple
+ Repeatable
- Exhaustive and slow
What are some positive and negative aspects with region proposal (hypothesis generation)?
+ Fast execution
+ Fewer candidate boxes/regions
- Random, not repeatable
- Requires preprocessing
List some examples of hypothesis description and scoring methods
1) HOG based template
2) HOG based template + parts
3) CNN features
How does the Dalal-Triggs Pedestrian Detector work?
1) Input image
2) Normalize gamma & colour
3) Compute gradients
4) Divide into cells and compute magnitude and angle
5) Normalize blocks of cells
6) Collect HOG's over detection window (concatenate each block into a feature vector)
7) Feed the feature vector into a SVM
8) Classify if person or not
How does Deformable part based detectors work?
• It defines objects by a collection of parts models by:
1) Appearance
2) Spatial configuration of parts (how they are spatial position relative to each other)
How does R-CNN works?
• It uses Region proposal + CNNs
1) Inputs an image
2) Extract region proposals of the image (~2k)
3) Feed region proposals into CNN
4) CNN classifies region
How many features (cascade layers) does a real-time Viola-Jones detector use?
36 layers
How does the classifier in Viola-Jones Face detection work?
It's a linear combination of weak classifiers that are optimized using Adaboost
Recommended textbook explanations
Computer Organization and Design MIPS Edition: The Hardware/Software Interface
5th Edition
David A. Patterson, John L. Hennessy
220 explanations
Introduction to Algorithms
3rd Edition
Charles E. Leiserson, Clifford Stein, Ronald L. Rivest, Thomas H. Cormen
709 explanations
Introduction to the Theory of Computation
3rd Edition
Michael Sipser
389 explanations
Operating System Concepts
9th Edition
Abraham Silberschatz, Greg Gagne, Peter B. Galvin
483 explanations
Sets with similar terms
Sensation and Perception, Ch. 4 Part 1
11 terms
Physics
18 terms
reflection and mirrors
42 terms
Optics
19 terms
Sets found in the same folder
Lecture 1
14 terms
Lecture 2 - Feature Descriptors
43 terms
Lecture 3 - Convolutional Neural Networks
31 terms
Lecture 4 - Image classification with convolutiona…
30 terms
Other sets by this creator
Lecture 8
14 terms
Lecture 7
18 terms
Lecture 6
8 terms
Lecture 5
18 terms
Verified questions
COMPUTER SCIENCE
Let B and C be languages over $\Sigma=\{0,1\}$. Define $B \stackrel{1}{\leftarrow} C=\{w \in B |$ for some $y \in C$, strings w and y contain equal numbers of 1s}. Show that the class of regular languages is closed under the $\leftarrow^{1}$ operation.
COMPUTER SCIENCE
Let $$ f(x)=\left\{\begin{array}{ll}{3 x+1} & {\mathrm { \ for \ odd \ } x} \\ {x / 2} & {\mathrm { \ for \ even \ } x}\end{array}\right. $$ for any natural number x. If you start with an integer x and iterate f, you obtain a sequence, x, f(x), f(f(x)), . . . . Stop if you ever hit 1. For example, if x = 17, you get the sequence 17, 52, 26, 13, 40, 20, 10, 5, 16, 8, 4, 2, 1. Extensive computer tests have shown that every starting point between 1 and a large positive integer gives a sequence that ends in 1. But the question of whether all positive starting points end up at 1 is unsolved; it is called the 3x+1 problem. Suppose that $A_{\mathrm{TM}}$ were decidable by a TM H. Use H to describe a TM that is guaranteed to state the answer to the 3x+1 problem.
COMPUTER SCIENCE
Design and implement a simulation of the game of volleyball. Normal volleyball is played like racquetball, in that a team can only score points when it is serving. Games are played to 15, but must be won by at least two points.
COMPUTER SCIENCE
Suppose that we have a set of activities to schedule among a large number of lecture halls, where any activity can take place in any lecture hall. We wish to schedule all the activities using as few lecture halls as possible. Give an efficient greedy algorithm to determine which activity should use which lecture hall. (This problem is also known as the interval-graph coloring problem. We can create an interval graph whose vertices are the given activities and whose edges connect incompatible activities. The smallest number of colors required to color every vertex so that no two adjacent vertices have the same color corresponds to finding the fewest lecture halls needed to schedule all of the given activities.)
Other Quizlet sets
Quiz 1: Components of Fitness
24 terms
Psych 102- Test 2
120 terms
VOCAB: Ch 15
45 terms
Astronomy Chapter 10
103 terms